via Stanford University
Today’s electronics waste energy by using separate chips to process and store data. New algorithms enable energy-efficient hybrids to work together as one mega-chip.
Smartwatches and other battery-powered electronics would be even smarter if they could run AI algorithms.
But efforts to build AI-capable chips for mobile devices have so far hit a wall — the so-called “memory wall” that separates data processing and memory chips that must work together to meet the massive and continually growing computational demands imposed by AI.
“Transactions between processors and memory can consume 95 percent of the energy needed to do machine learning and AI, and that severely limits battery life,” said computer scientist Subhasish Mitra, senior author of a new study published in Nature Electronics.
Now, a team that includes Stanford School of Engineering computer scientist Mary Wootters and electrical engineer H.-S. Philip Wong has designed a system that can run AI tasks faster, and with less energy, by harnessing eight hybrid chips, each with its own data processor built right next to its own memory storage.
This paper builds on the team’s prior development of a new memory technology, called RRAM, that stores data even when power is switched off — like flash memory — only faster and more energy efficiently. Their RRAM advance enabled the Stanford researchers to develop an earlier generation of hybrid chips that worked alone. Their latest design incorporates a critical new element: algorithms that meld the eight, separate hybrid chips into one energy-efficient AI-processing engine.
“If we could have built one massive, conventional chip with all the processing and memory needed, we’d have done so, but the amount of data it takes to solve AI problems makes that a dream,” Mitra said. “Instead, we trick the hybrids into thinking they’re one chip, which is why we call this the Illusion System.”
The researchers developed Illusion as part of the Electronics Resurgence Initiative (ERI), a $1.5 billion program sponsored by the Defense Advanced Research Projects Agency. DARPA, which helped spawn the internet more than 50 years ago, is supporting research investigating workarounds to Moore’s Law, which has driven electronic advances by shrinking transistors. But transistors can’t keep shrinking forever.
“To surpass the limits of conventional electronics, we’ll need new hardware technologies and new ideas about how to use them,” Wootters said.
The Stanford-led team built and tested its prototype with help from collaborators at the French research institute CEA-Leti and at Nanyang Technological University in Singapore. The team’s eight-chip system is just the beginning. In simulations, the researchers showed how systems with 64 hybrid chips could run AI applications seven times faster than current processors, using one-seventh as much energy.
Such capabilities could one day enable Illusion Systems to become the brains of augmented and virtual reality glasses that would use deep neural networks to learn by spotting objects and people in the environment, and provide wearers with contextual information — imagine an AR/VR system to help birdwatchers identify unknown specimens.
Stanford graduate student Robert Radway, who is first author of the Nature Electronics study, said the team also developed new algorithms to recompile existing AI programs, written for today’s processors, to run on the new multi-chip systems. Collaborators from Facebook helped the team test AI programs that validated their efforts. Next steps include increasing the processing and memory capabilities of individual hybrid chips and demonstrating how to mass produce them cheaply.
“The fact that our fabricated prototype is working as we expected suggests we’re on the right track,” said Wong, who believes Illusion Systems could be ready for marketability within three to five years.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Items tagged with Intel
It's barely been four weeks since we wrote about a WHQL-certified Intel Arc graphics driver purporting to deliver massive performance gains by triple-digit percentages in some titles. Our coverage ...
- Alibaba Leads Record Deal to Create $2.5 Billion China AI Firm
Alibaba Group Holding Ltd. led the largest single financing round for a Chinese artificial intelligence startup, the latest in a string of sizeable investments that suggest the e-commerce firm is ...
- Intel’s secretive Knights Mill mega-chip will challenge GPUs for AI domination
The U.S. will go ahead with its plan to hand over oversight of the internet's domain name system functions to a multistakeholder body on Oct. 1, despite fierce opposition from some lawmakers and ...
- Intel tunes its mega-chip for machine learning
LizardStresser, the DDoS malware for Linux systems written by the infamous Lizard Squad attacker group, was used over the past year to create over 100 botnets, some built almost exclusively from ...
- Intel Reveals Why It's Delaying A $20 Billion Mega Chip Plant In Ohio
Intel’s plans to complete the construction of a chip plant in Ohio has hit a delay, with the company now expecting for the new facility to be up and running by late 2026, according to a report ...
Go deeper with Google Headlines on:
[google_news title=”” keyword=”mega-chip” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
- Second Cambridgeshire Co-op targeted in ram raid in less than a week
A Co-op in Cambridge has become the second in less than a week to be hit by a ram raid. The Marleigh Avenue store was targeted in the early hours of Sunday morning (February 25). Items were taken, but ...
- Weebit Nano demonstrates ReRAM high reliability and performance
Weebit Nano, the developer of advanced memory technologies, has been able to demonstrate the high endurance and reliability of its Resistive Random-Access Memory (ReRAM or RRAM) in extended automotive ...
- Weebit Nano demonstrates performance of its ReRAM under extended automotive conditions
is demonstrating the high endurance and reliability of its Resistive Random-Access Memory (ReRAM or RRAM) in extended automotive conditions, including high temperatures of 150 degrees Celsius and ...
Apple's generative AI development attempts get a huge resource push as Apple shelves its project to build a semi-autonomous vehicle, though the company will reap benefits from that attempt for a ...
- All eyes on PML-N, PPP power-sharing formula
Khurram Virk (PP-48) from Sialkot, Zulfiqar Ali Shah (PP-96) from Chiniot, Rana Fayyaz (PP-49) from Pasrur, and Saqib Chadhar (PP-97) from Chiniot Their decision to join the PML-N was initially ...
Go deeper with Google Headlines on:
[google_news title=”” keyword=”RRAM” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]